A GENERAL CLASS OF LOWER BOUNDS ON THE PROBABILITY OF ERROR IN MULTIPLE HYPOTHESIS TESTING

被引：0

作者：

Routtenberg, Tirza ^{[1
]}

Tabrikian, Joseph ^{[1
]}

机构：

[1] Ben Gurion Univ Negev, Dept Elect & Comp Engn, IL-84105 Beer Sheva, Israel

来源：

2008 IEEE 25TH CONVENTION OF ELECTRICAL AND ELECTRONICS ENGINEERS IN ISRAEL, VOLS 1 AND 2 | 2008年

关键词：

MAP; detection; lower bounds; hypothesis testing; probability of error;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, a new class of lower bounds on the probability of error for m-ary hypothesis tests is proposed. Computation of the minimum probability of error which is attained by the maximum a-posteriori probability (MAP) criterion, is usually not tractable. The new class is derived using Holder's inequality. The bounds in this class are continuous and differentiable function of the conditional probability of error and they provide good prediction of the minimum probability of error in multiple hypothesis testing. It is shown that for binary hypothesis testing problem this bound asymptotically coincides with the optimum probability of error provided by the MAP criterion. This bound is compared with other existing lower bounds in several typical detection and classification problems in terms of tightness and computational complexity.

引用

页码：730 / 734

页数：5

共 16 条

[1]

Abramowitz M., 1964, HDB MATH FUNCTIONS F, V55

[2]

[Anonymous], P 44 ALL C COMM CONT

[3] Arbitrarily tight upper and lower bounds on the Bayesian probability of error [J].

AviItzhak, H ;

Diep, T .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1996, 18 (01) :89-91

[4] IMPROVED LOWER BOUNDS ON SIGNAL PARAMETER ESTIMATION [J].

CHAZAN, D ;

ZAKAI, M ;

ZIV, J .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1975, 21 (01) :90-93

[5] NEW CLASS OF BOUNDS ON BAYES RISK IN MULTIHYPOTHESIS PATTERN-RECOGNITION [J].

DEVIJVER, PA .

IEEE TRANSACTIONS ON COMPUTERS, 1974, C 23 (01) :70-80

[6]

FANO RM, 1952, CLASS NOTES TRANSMIS

[7] RELATIONS BETWEEN ENTROPY AND ERROR-PROBABILITY [J].

FEDER, M ;

MERHAV, N .

IEEE TRANSACTIONS ON INFORMATION THEORY, 1994, 40 (01) :259-266

[8]

HAN TS, 1994, IEEE T INFORM THEORY, V40, P1247, DOI 10.1109/18.335943

[9]

Hardy GH., 1988, Inequalities

[10]

HASHLAMOUN WA, 1991, THESIS SYRACUSE U SY

← 1 2 →